Computers & Electrical Engineering最新文献_第3页

Joint detection and localization of False Data Injection Attacks in smart grids: An enhanced state estimation approach 智能电网中虚假数据注入攻击的联合检测与定位：增强型状态估计方法

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-11-09 DOI: 10.1016/j.compeleceng.2024.109834

Guoqing Zhang, Wengen Gao, Yunfei Li, Yixuan Liu, Xinxin Guo, Wenlong Jiang

The transition to smart grids introduces significant cybersecurity vulnerabilities, particularly with the rise of False Data Injection Attacks (FDIAs). These attacks allow malicious actors to manipulate sensor data, alter the internal state of the grid, and bypass traditional Bad Data Detection (BDD) systems. FDIAs pose a serious threat to grid security, potentially leading to incorrect state estimation and destabilization of the power system, which could result in system outages and economic losses. To address this challenge, this paper proposes a novel detection and localization method. First, false data and measurement errors are modeled as non-Gaussian noise. Recognizing the limitations of the traditional Extended Kalman Filter (EKF) under non-Gaussian conditions, the Maximum Correntropy Criterion (MCC) is integrated into the EKF to improve the robustness of state estimation. Additionally, the Maximum Correntropy Criterion Extended Kalman Filter (MCCEKF) is combined with Weighted Least Squares (WLS), and cosine similarity is introduced to quantify the differences between these two estimators for FDIA detection. A partition approach is then used to construct a logical localization matrix, with cosine similarity detection applied in each section to generate a detection matrix. By performing a logical AND operation on these matrices, the attacked bus is identified. Simulations on IEEE-14-bus and IEEE-30-bus systems validate the proposed approach, demonstrating its effectiveness in reliably detecting and localizing FDIAs in smart grids.

向智能电网的过渡带来了重大的网络安全漏洞，特别是随着虚假数据注入攻击（FDIAs）的兴起。这些攻击允许恶意行为者篡改传感器数据、改变电网内部状态并绕过传统的不良数据检测（BDD）系统。FDIA 对电网安全构成严重威胁，可能导致不正确的状态估计和电力系统不稳定，从而造成系统中断和经济损失。为应对这一挑战，本文提出了一种新型检测和定位方法。首先，错误数据和测量误差被建模为非高斯噪声。认识到传统的扩展卡尔曼滤波器（EKF）在非高斯条件下的局限性，最大熵准则（MCC）被集成到 EKF 中，以提高状态估计的鲁棒性。此外，最大熵准则扩展卡尔曼滤波器（MCCEKF）与加权最小二乘法（WLS）相结合，并引入余弦相似性来量化这两种估计器在 FDIA 检测中的差异。然后使用分区方法构建逻辑定位矩阵，并在每个部分应用余弦相似性检测生成检测矩阵。通过对这些矩阵执行逻辑 AND 运算，就能识别出被攻击的总线。在 IEEE-14 总线和 IEEE-30 总线系统上进行的仿真验证了所提出的方法，证明了它在智能电网中可靠检测和定位 FDIA 的有效性。

{"title":"Joint detection and localization of False Data Injection Attacks in smart grids: An enhanced state estimation approach","authors":"Guoqing Zhang, Wengen Gao, Yunfei Li, Yixuan Liu, Xinxin Guo, Wenlong Jiang","doi":"10.1016/j.compeleceng.2024.109834","DOIUrl":"10.1016/j.compeleceng.2024.109834","url":null,"abstract":"<div><div>The transition to smart grids introduces significant cybersecurity vulnerabilities, particularly with the rise of False Data Injection Attacks (FDIAs). These attacks allow malicious actors to manipulate sensor data, alter the internal state of the grid, and bypass traditional Bad Data Detection (BDD) systems. FDIAs pose a serious threat to grid security, potentially leading to incorrect state estimation and destabilization of the power system, which could result in system outages and economic losses. To address this challenge, this paper proposes a novel detection and localization method. First, false data and measurement errors are modeled as non-Gaussian noise. Recognizing the limitations of the traditional Extended Kalman Filter (EKF) under non-Gaussian conditions, the Maximum Correntropy Criterion (MCC) is integrated into the EKF to improve the robustness of state estimation. Additionally, the Maximum Correntropy Criterion Extended Kalman Filter (MCCEKF) is combined with Weighted Least Squares (WLS), and cosine similarity is introduced to quantify the differences between these two estimators for FDIA detection. A partition approach is then used to construct a logical localization matrix, with cosine similarity detection applied in each section to generate a detection matrix. By performing a logical AND operation on these matrices, the attacked bus is identified. Simulations on IEEE-14-bus and IEEE-30-bus systems validate the proposed approach, demonstrating its effectiveness in reliably detecting and localizing FDIAs in smart grids.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109834"},"PeriodicalIF":4.0,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An optimized multilayer perceptron-based network intrusion detection using Gray Wolf Optimization 基于多层感知器的网络入侵检测灰狼优化法

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-11-08 DOI: 10.1016/j.compeleceng.2024.109838

Asad Ali , Muhammad Assam , Faheem Ullah Khan , Yazeed Yasin Ghadi , Zhumazhan Nurdaulet , Alibiyeva Zhibek , Syed Yaqub Shah , Tahani Jaser Alahmadi

The exponential growth in the use of network services through the design of various network infrastructures, has led to increased complexities and challenges in the network. A major problem in computer networks is privacy and security breach. Cyber attackers exploit loopholes to infiltrate and disrupt the operation of the network through various attacks. Anomaly-based intrusion detection often employs Artificial Neural Network techniques like Multi-layer Perceptron (MLP) to classify malicious and legitimate traffic. Nevertheless, these techniques are vulnerable to overfitting and require extensive labeled data and computational resources. Consequently, this reduces the accuracy of intrusion detection systems and increases the error detection rate. To minimize the error detection rate of the intrusion detection system, it is necessary to optimize the connection parameters of the MLP neural network such as weights and biases. To this end, we proposed an optimized MLP-based Intrusion Detection using Gray Wolf Optimization (GWOMLP-IDS) to optimize the learning process of the MLP neural network by optimizing weights and biases. GWO aims to select an optimal connection parameter during the learning process to minimize the error rate of intrusion detection. Extensive simulations in Python reveal the effectiveness of the proposed approach in terms of designated performance metrics.

通过设计各种网络基础设施，网络服务的使用呈指数级增长，这导致网络的复杂性和挑战性不断增加。计算机网络的一个主要问题是隐私和安全漏洞。网络攻击者利用漏洞进行渗透，通过各种攻击破坏网络的运行。基于异常的入侵检测通常采用多层感知器（MLP）等人工神经网络技术对恶意和合法流量进行分类。然而，这些技术容易出现过拟合，而且需要大量标注数据和计算资源。因此，这降低了入侵检测系统的准确性，增加了错误检测率。为了最大限度地降低入侵检测系统的错误检测率，有必要优化 MLP 神经网络的连接参数，如权重和偏置。为此，我们提出了基于 MLP 的灰狼优化入侵检测（GWOMLP-IDS），通过优化权重和偏置来优化 MLP 神经网络的学习过程。GWOMLP-IDS 的目的是在学习过程中选择最佳连接参数，从而最大限度地降低入侵检测的错误率。在 Python 中进行的大量模拟揭示了所提方法在指定性能指标方面的有效性。

{"title":"An optimized multilayer perceptron-based network intrusion detection using Gray Wolf Optimization","authors":"Asad Ali , Muhammad Assam , Faheem Ullah Khan , Yazeed Yasin Ghadi , Zhumazhan Nurdaulet , Alibiyeva Zhibek , Syed Yaqub Shah , Tahani Jaser Alahmadi","doi":"10.1016/j.compeleceng.2024.109838","DOIUrl":"10.1016/j.compeleceng.2024.109838","url":null,"abstract":"<div><div>The exponential growth in the use of network services through the design of various network infrastructures, has led to increased complexities and challenges in the network. A major problem in computer networks is privacy and security breach. Cyber attackers exploit loopholes to infiltrate and disrupt the operation of the network through various attacks. Anomaly-based intrusion detection often employs Artificial Neural Network techniques like Multi-layer Perceptron (MLP) to classify malicious and legitimate traffic. Nevertheless, these techniques are vulnerable to overfitting and require extensive labeled data and computational resources. Consequently, this reduces the accuracy of intrusion detection systems and increases the error detection rate. To minimize the error detection rate of the intrusion detection system, it is necessary to optimize the connection parameters of the MLP neural network such as weights and biases. To this end, we proposed an optimized MLP-based Intrusion Detection using Gray Wolf Optimization (GWOMLP-IDS) to optimize the learning process of the MLP neural network by optimizing weights and biases. GWO aims to select an optimal connection parameter during the learning process to minimize the error rate of intrusion detection. Extensive simulations in Python reveal the effectiveness of the proposed approach in terms of designated performance metrics.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109838"},"PeriodicalIF":4.0,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimization and uncertainty analysis of hybrid energy systems using Monte Carlo simulation integrated with genetic algorithm 利用蒙特卡罗模拟与遗传算法相结合，对混合能源系统进行优化和不确定性分析

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-11-07 DOI: 10.1016/j.compeleceng.2024.109833

Hassan M. Hussein Farh , Abdullrahman A. Al-Shamma'a , Fahad Alaql , Hammed Olabisi Omotoso , Walied Alfraidi , Mohamed A. Mohamed

This study investigates the optimization of hybrid energy systems (HES) composed of wind turbines, battery banks, and diesel generators, focusing on addressing the challenges posed by wind speed uncertainty. This research contributes significantly to the field by developing a novel methodology that combines uncertainty analysis with hybrid optimization techniques to improve the reliability and cost-effectiveness of HES. The findings revealed that initial simulations without renewable energy sources result in high diesel consumption, with fuel usage reaching 534,810 liters per year and associated carbon emissions totaling 797,070 kg/year. Through optimization, an economically viable configuration is identified, consisting of 37 battery banks, two 250 kW wind turbines, and a 340-kW diesel generator, achieving an Annualized System Cost (ASC) of $166,500 and a Cost of Energy (COE) of $0.1480/kWh. The Monte Carlo simulations indicate a most probable COE of $0.1450/kWh for the wind turbine/battery/diesel system, occurring with an 8.3 % probability, while approximately 90 % of COE values fall below $0.1669/kWh. The average COE is $0.14834/kWh, with a minimum of $0.12163/kWh. The Renewable Energy Fraction (REF) spans from 28 % to 97 %, with an average of 64 % and a standard deviation error of 9.6 % at a 95 % confidence level. The results underscore the potential implications for informing policymakers and industry leaders about the design and evaluation of HES under uncertain environmental conditions. By addressing the limitations of current approaches, this work contributes valuable insights into the economic, environmental, and social dimensions of hybrid renewable energy systems.

本研究探讨了由风力涡轮机、电池组和柴油发电机组成的混合能源系统（HES）的优化问题，重点是应对风速不确定性带来的挑战。这项研究通过开发一种新方法，将不确定性分析与混合优化技术相结合，提高了混合能源系统的可靠性和成本效益，为该领域做出了重大贡献。研究结果表明，在不使用可再生能源的情况下，初始模拟的柴油消耗量很高，每年的燃料用量达到 534,810 升，相关的碳排放量共计 797,070 千克/年。通过优化，确定了一种经济可行的配置，包括 37 个电池组、两台 250 千瓦的风力涡轮机和一台 340 千瓦的柴油发电机，年化系统成本 (ASC) 为 166,500 美元，能源成本 (COE) 为 0.1480 美元/千瓦时。蒙特卡罗模拟显示，风力涡轮机/电池/柴油系统的最可能 COE 为 0.1450 美元/千瓦时，发生概率为 8.3%，而约 90% 的 COE 值低于 0.1669 美元/千瓦时。平均 COE 为 0.14834 美元/千瓦时，最低为 0.12163 美元/千瓦时。可再生能源比例 (REF) 从 28% 到 97% 不等，平均为 64%，在 95% 的置信水平下，标准偏差误差为 9.6%。这些结果强调了在不确定的环境条件下，为政策制定者和行业领导者提供有关设计和评估 HES 的潜在影响。通过解决当前方法的局限性，这项工作为混合可再生能源系统的经济、环境和社会层面提供了宝贵的见解。

{"title":"Optimization and uncertainty analysis of hybrid energy systems using Monte Carlo simulation integrated with genetic algorithm","authors":"Hassan M. Hussein Farh , Abdullrahman A. Al-Shamma'a , Fahad Alaql , Hammed Olabisi Omotoso , Walied Alfraidi , Mohamed A. Mohamed","doi":"10.1016/j.compeleceng.2024.109833","DOIUrl":"10.1016/j.compeleceng.2024.109833","url":null,"abstract":"<div><div>This study investigates the optimization of hybrid energy systems (HES) composed of wind turbines, battery banks, and diesel generators, focusing on addressing the challenges posed by wind speed uncertainty. This research contributes significantly to the field by developing a novel methodology that combines uncertainty analysis with hybrid optimization techniques to improve the reliability and cost-effectiveness of HES. The findings revealed that initial simulations without renewable energy sources result in high diesel consumption, with fuel usage reaching 534,810 liters per year and associated carbon emissions totaling 797,070 kg/year. Through optimization, an economically viable configuration is identified, consisting of 37 battery banks, two 250 kW wind turbines, and a 340-kW diesel generator, achieving an Annualized System Cost (ASC) of $166,500 and a Cost of Energy (COE) of $0.1480/kWh. The Monte Carlo simulations indicate a most probable COE of $0.1450/kWh for the wind turbine/battery/diesel system, occurring with an 8.3 % probability, while approximately 90 % of COE values fall below $0.1669/kWh. The average COE is $0.14834/kWh, with a minimum of $0.12163/kWh. The Renewable Energy Fraction (REF) spans from 28 % to 97 %, with an average of 64 % and a standard deviation error of 9.6 % at a 95 % confidence level. The results underscore the potential implications for informing policymakers and industry leaders about the design and evaluation of HES under uncertain environmental conditions. By addressing the limitations of current approaches, this work contributes valuable insights into the economic, environmental, and social dimensions of hybrid renewable energy systems.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109833"},"PeriodicalIF":4.0,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimization and energy management strategies, challenges, advances, and prospects in electric vehicles and their charging infrastructures: A comprehensive review 电动汽车及其充电基础设施的优化和能源管理战略、挑战、进展和前景：全面回顾

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-11-07 DOI: 10.1016/j.compeleceng.2024.109842

Jamiu Oladigbolu , Asad Mujeeb , Li Li

Electric vehicles (EVs) are at the forefront of global efforts to reduce greenhouse gas emissions and transition to sustainable energy systems. This review comprehensively examines the optimization and energy management strategies for EVs and their charging infrastructure, focusing on technological advancements, persistent challenges, and future prospects. By the end of 2023, the number of electric cars on the road globally reached 40 million, with 14 million new registrations recorded in 2023 alone—95% of which were in China, Europe, and the United States. Governments across the globe have introduced incentives and policies to promote EV adoption, and by 2030, EVs are expected to comprise a significant portion of light-duty vehicles in major regions. Despite these encouraging developments, challenges such as range anxiety, the relatively low energy density of 200–300 Wh/kg in Li-ion batteries (compared to 13,000 Wh/kg for petroleum), and insufficient public charging infrastructure remain key barriers to widespread EV adoption. This review also explores the critical role of smart grid technologies, vehicle-to-grid (V2G) systems, and renewable energy integration in supporting the growing EV market. V2G technologies are projected to enhance grid stability by 20–30% and reduce operational costs by 10–15% through load balancing and real-time energy price forecasting. By thoroughly analyzing optimization techniques such as load balancing, dynamic scheduling, and real-time energy management, this paper offers a roadmap for researchers, policymakers, and industry stakeholders to accelerate the integration of EVs into global energy systems and enhance sustainability in urban transportation networks.

电动汽车（EV）是全球减少温室气体排放和向可持续能源系统过渡的最前沿。本综述全面探讨了电动汽车及其充电基础设施的优化和能源管理策略，重点关注技术进步、持续挑战和未来前景。到 2023 年底，全球上路行驶的电动汽车数量将达到 4000 万辆，仅 2023 年就有 1400 万辆新注册，其中 95% 在中国、欧洲和美国。全球各国政府纷纷出台激励措施和政策，推动电动汽车的普及，预计到 2030 年，电动汽车将在主要地区的轻型汽车中占据相当大的比例。尽管这些发展令人鼓舞，但诸如续航里程焦虑症、锂离子电池 200-300 Wh/kg 的相对较低能量密度（相比之下，石油电池为 13,000 Wh/kg）以及公共充电基础设施不足等挑战仍然是电动汽车普及的主要障碍。本综述还探讨了智能电网技术、车辆到电网（V2G）系统和可再生能源集成在支持日益增长的电动汽车市场中的关键作用。通过负载平衡和实时能源价格预测，V2G 技术预计可将电网稳定性提高 20-30%，并将运营成本降低 10-15%。通过深入分析负载平衡、动态调度和实时能源管理等优化技术，本文为研究人员、政策制定者和行业利益相关者提供了一个路线图，以加快电动汽车与全球能源系统的整合，提高城市交通网络的可持续性。

{"title":"Optimization and energy management strategies, challenges, advances, and prospects in electric vehicles and their charging infrastructures: A comprehensive review","authors":"Jamiu Oladigbolu , Asad Mujeeb , Li Li","doi":"10.1016/j.compeleceng.2024.109842","DOIUrl":"10.1016/j.compeleceng.2024.109842","url":null,"abstract":"<div><div>Electric vehicles (EVs) are at the forefront of global efforts to reduce greenhouse gas emissions and transition to sustainable energy systems. This review comprehensively examines the optimization and energy management strategies for EVs and their charging infrastructure, focusing on technological advancements, persistent challenges, and future prospects. By the end of 2023, the number of electric cars on the road globally reached 40 million, with 14 million new registrations recorded in 2023 alone—95% of which were in China, Europe, and the United States. Governments across the globe have introduced incentives and policies to promote EV adoption, and by 2030, EVs are expected to comprise a significant portion of light-duty vehicles in major regions. Despite these encouraging developments, challenges such as range anxiety, the relatively low energy density of 200–300 Wh/kg in Li-ion batteries (compared to 13,000 Wh/kg for petroleum), and insufficient public charging infrastructure remain key barriers to widespread EV adoption. This review also explores the critical role of smart grid technologies, vehicle-to-grid (V2G) systems, and renewable energy integration in supporting the growing EV market. V2G technologies are projected to enhance grid stability by 20–30% and reduce operational costs by 10–15% through load balancing and real-time energy price forecasting. By thoroughly analyzing optimization techniques such as load balancing, dynamic scheduling, and real-time energy management, this paper offers a roadmap for researchers, policymakers, and industry stakeholders to accelerate the integration of EVs into global energy systems and enhance sustainability in urban transportation networks.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109842"},"PeriodicalIF":4.0,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-timescale modeling and order reduction towards stability analysis of isolated microgrids 面向孤立微电网稳定性分析的多时标建模和阶次缩减

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-11-07 DOI: 10.1016/j.compeleceng.2024.109835

Chaofeng Yan , Yang Han , Ensheng Zhao , Yuxiang Liu , Ping Yang , Congling Wang , Amr S. Zalhaf

Microgrids incorporate a significant proportion of renewable energy sources and power electronic converters in the energy conversion process, creating a sustainable and clean energy infrastructure. However, the multi-timescale dynamics of microgrids are interactively coupled under a nonlinear structure, which makes it difficult to gain insight into the instability mechanisms without a high-fidelity reduced-order model that preserves the main dynamic behaviors of the system. For the isolated AC microgrid dominated by voltage source inverters (VSI), a detailed state-space model of the system, including the inverter, network, and load, is first developed. Based on this model, the eigenvalue analysis is carried out, and a participation factor analysis tool is also utilized to identify the relevant dynamics that have a strong impact on the system's dominant mode. Furthermore, to simplify the system modeling process without losing essential dynamic interactions, a novel multi-timescale coupled reduced-order model is proposed using a transfer function-based order reduction method, which retains the open-loop gain characteristics to preserve the critical couplings between fast inner loop dynamics and slow droop control dynamics. Finally, the accuracy of the reduced-order model is verified by comparing it with the detailed model and the conventional singular perturbation reduced-order model through eigenvalue distribution and time-domain simulation analysis.

微电网在能源转换过程中结合了大量可再生能源和电力电子转换器，从而创建了一种可持续的清洁能源基础设施。然而，在非线性结构下，微电网的多时标动态是交互耦合的，如果没有一个能保留系统主要动态行为的高保真降阶模型，就很难深入了解其不稳定机制。对于由电压源逆变器（VSI）主导的隔离交流微电网，首先要建立一个详细的系统状态空间模型，包括逆变器、网络和负载。在此模型的基础上，进行特征值分析，并利用参与因子分析工具确定对系统主导模式有重大影响的相关动态。此外，为了简化系统建模过程而不丢失重要的动态交互，我们提出了一种新颖的多时标耦合降阶模型，该模型采用了基于传递函数的降阶方法，保留了开环增益特性，从而保留了快速内环动态和慢速下垂控制动态之间的关键耦合。最后，通过特征值分布和时域仿真分析，与详细模型和传统的奇异扰动减阶模型进行比较，验证了减阶模型的准确性。

{"title":"Multi-timescale modeling and order reduction towards stability analysis of isolated microgrids","authors":"Chaofeng Yan , Yang Han , Ensheng Zhao , Yuxiang Liu , Ping Yang , Congling Wang , Amr S. Zalhaf","doi":"10.1016/j.compeleceng.2024.109835","DOIUrl":"10.1016/j.compeleceng.2024.109835","url":null,"abstract":"<div><div>Microgrids incorporate a significant proportion of renewable energy sources and power electronic converters in the energy conversion process, creating a sustainable and clean energy infrastructure. However, the multi-timescale dynamics of microgrids are interactively coupled under a nonlinear structure, which makes it difficult to gain insight into the instability mechanisms without a high-fidelity reduced-order model that preserves the main dynamic behaviors of the system. For the isolated AC microgrid dominated by voltage source inverters (VSI), a detailed state-space model of the system, including the inverter, network, and load, is first developed. Based on this model, the eigenvalue analysis is carried out, and a participation factor analysis tool is also utilized to identify the relevant dynamics that have a strong impact on the system's dominant mode. Furthermore, to simplify the system modeling process without losing essential dynamic interactions, a novel multi-timescale coupled reduced-order model is proposed using a transfer function-based order reduction method, which retains the open-loop gain characteristics to preserve the critical couplings between fast inner loop dynamics and slow droop control dynamics. Finally, the accuracy of the reduced-order model is verified by comparing it with the detailed model and the conventional singular perturbation reduced-order model through eigenvalue distribution and time-domain simulation analysis.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109835"},"PeriodicalIF":4.0,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel Distributed Denial of Service attack defense scheme for Software-Defined Networking using Packet-In message and frequency domain analysis 利用包入信息和频域分析为软件定义网络设计的新型分布式拒绝服务攻击防御方案

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-11-06 DOI: 10.1016/j.compeleceng.2024.109827

Ramin Fadaei Fouladi , Leyli Karaçay , Utku Gülen , Elif Ustundag Soykan

Software-Defined Networking (SDN) enhances network management by improving adaptability, flexibility, and scalability. However, its centralized controller is vulnerable to Distributed Denial of Service (DDoS) attacks that can disrupt network availability. This study introduces a novel real-time DDoS detection scheme integrated into the SDN controller. The scheme uses a two-step process to analyze Packet-In messages in both time and frequency domains. A time-series is generated by sampling the number of Packet-In messages at specific time intervals, which is compared against a predefined threshold. If exceeded, frequency domain analysis is applied to extract features, which are then used by Machine Learning (ML) algorithms to identify DDoS attacks. The scheme achieves 99.85% accuracy in distinguishing normal traffic from attack traffic, demonstrating its effectiveness in safeguarding SDN environments from DDoS threats.

软件定义网络（SDN）通过提高适应性、灵活性和可扩展性来加强网络管理。然而，其集中式控制器容易受到分布式拒绝服务（DDoS）攻击，从而破坏网络可用性。本研究介绍了一种集成到 SDN 控制器中的新型实时 DDoS 检测方案。该方案采用两步流程来分析时域和频域中的包入信息。通过对特定时间间隔内的包入信息数量进行采样，生成时间序列，并将其与预定义的阈值进行比较。如果超过阈值，则应用频域分析提取特征，然后由机器学习（ML）算法用于识别 DDoS 攻击。该方案在区分正常流量和攻击流量方面达到了 99.85% 的准确率，证明了其在保护 SDN 环境免受 DDoS 威胁方面的有效性。

引用次数: 0

A gradual approach to knowledge distillation in deep supervised hashing for large-scale image retrieval 用于大规模图像检索的深度监督哈希算法中的渐进式知识提炼方法

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-11-06 DOI: 10.1016/j.compeleceng.2024.109799

Abid Hussain , Heng-Chao li , Mehboob Hussain , Muqadar Ali , Shaheen Abbas , Danish Ali , Amir Rehman

Deep learning-based hashing methods have emerged as superior techniques for large-scale image retrieval, surpassing non-deep and unsupervised algorithms. However, most hashing models do not consider memory usage and computational costs, which hinders their use on resource-constrained devices. This paper proposes an Optimized Knowledge Distillation (OKD) approach for training compact deep supervised hashing models to address this issue. OKD utilizes a unique growing teacher-student training strategy where an evolving teacher continuously imparts enriched knowledge to the student. The teacher and student networks are divided into blocks, with auxiliary training modules placed between corresponding blocks. These modules extract knowledge from intermediate layers to capture multifaceted relationships in data and enhance distillation. Furthermore, a noise- and background-reduction mask (NBRM) is employed to filter noise from transferred knowledge, promoting focus on discriminative features. During training, the student utilizes various sources of supervision, including dynamically improving the teacher's predictions, ground truths, and hash code matching. This assists the student in closely replicating the teacher's abilities despite using fewer parameters. Experimental evaluation on four benchmark datasets - CIFAR-10, CIFAR-100, NUS-WIDE, and ImageNet - demonstrates that OKD outperforms existing hashing methods. OKD achieves 92.98 %, 88.72 %, and 75.88 % mean average precision on CIFAR-10, NUS-WIDE, and ImageNet datasets, respectively, with up to 1.83 %, 1.69 %, and 0.80 % higher accuracy than the previous best methods, across different hash code lengths. By matching teacher ability using distilled knowledge, OKD addresses the barriers that prevent powerful models from being deployed on resource-constrained mobile/embedded platforms.

基于深度学习的散列方法已成为大规模图像检索的卓越技术，超越了非深度和无监督算法。然而，大多数散列模型没有考虑内存使用和计算成本，这阻碍了它们在资源受限设备上的应用。本文提出了一种优化知识蒸馏（OKD）方法，用于训练紧凑型深度监督散列模型，以解决这一问题。OKD 采用独特的成长型师生训练策略，即不断发展的教师不断向学生传授丰富的知识。教师和学生网络被划分为多个区块，并在相应的区块之间放置了辅助训练模块。这些模块从中间层提取知识，以捕捉数据中的多方面关系并加强提炼。此外，还采用了噪声和背景还原掩码（NBRM）来过滤传输知识中的噪声，从而促进对辨别特征的关注。在训练过程中，学生会利用各种监督来源，包括动态改进教师的预测、基本事实和哈希代码匹配。这有助于学生在使用较少参数的情况下密切复制教师的能力。在四个基准数据集（CIFAR-10、CIFAR-100、NUS-WIDE 和 ImageNet）上进行的实验评估表明，OKD 优于现有的散列方法。在 CIFAR-10、NUS-WIDE 和 ImageNet 数据集上，OKD 的平均精确度分别达到 92.98%、88.72% 和 75.88%，在不同哈希码长度的数据集上，其精确度分别比之前的最佳方法高出 1.83%、1.69% 和 0.80%。通过利用提炼的知识匹配教师能力，OKD 解决了妨碍在资源有限的移动/嵌入式平台上部署强大模型的障碍。

{"title":"A gradual approach to knowledge distillation in deep supervised hashing for large-scale image retrieval","authors":"Abid Hussain , Heng-Chao li , Mehboob Hussain , Muqadar Ali , Shaheen Abbas , Danish Ali , Amir Rehman","doi":"10.1016/j.compeleceng.2024.109799","DOIUrl":"10.1016/j.compeleceng.2024.109799","url":null,"abstract":"<div><div>Deep learning-based hashing methods have emerged as superior techniques for large-scale image retrieval, surpassing non-deep and unsupervised algorithms. However, most hashing models do not consider memory usage and computational costs, which hinders their use on resource-constrained devices. This paper proposes an Optimized Knowledge Distillation (OKD) approach for training compact deep supervised hashing models to address this issue. OKD utilizes a unique growing teacher-student training strategy where an evolving teacher continuously imparts enriched knowledge to the student. The teacher and student networks are divided into blocks, with auxiliary training modules placed between corresponding blocks. These modules extract knowledge from intermediate layers to capture multifaceted relationships in data and enhance distillation. Furthermore, a noise- and background-reduction mask (NBRM) is employed to filter noise from transferred knowledge, promoting focus on discriminative features. During training, the student utilizes various sources of supervision, including dynamically improving the teacher's predictions, ground truths, and hash code matching. This assists the student in closely replicating the teacher's abilities despite using fewer parameters. Experimental evaluation on four benchmark datasets - CIFAR-10, CIFAR-100, NUS-WIDE, and ImageNet - demonstrates that OKD outperforms existing hashing methods. OKD achieves 92.98 %, 88.72 %, and 75.88 % mean average precision on CIFAR-10, NUS-WIDE, and ImageNet datasets, respectively, with up to 1.83 %, 1.69 %, and 0.80 % higher accuracy than the previous best methods, across different hash code lengths. By matching teacher ability using distilled knowledge, OKD addresses the barriers that prevent powerful models from being deployed on resource-constrained mobile/embedded platforms.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109799"},"PeriodicalIF":4.0,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-agent deep reinforcement learning based multiple access for underwater cognitive acoustic sensor networks 基于多代理深度强化学习的水下认知声学传感器网络多重接入

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-11-06 DOI: 10.1016/j.compeleceng.2024.109819

Yuzhi Zhang, Xiang Han, Ran Bai, Menglei Jia

Considering the challenges posed by the significant propagation delays inherent in underwater cognitive acoustic sensor networks, this paper explores the application of multi-agent deep reinforcement learning for the design of multiple access protocols. We deal with the problem of sharing channels and time slots among multiple sensor nodes that adopt different time-slotted MAC protocols. The multiple intelligent nodes can independently learn the strategies for accessing available idle time slots through the proposed multi-agent deep reinforcement learning (DRL) based multiple access control (MDRL-MAC) protocol. Considering the long propagation delay associated with underwater acoustic channels, we reformulate proper state, action, and reward within the DRL framework to address the multiple access challenges and optimize network throughput. To mitigate the decision deviation stemming from partial observability, the gated recurrent unit (GRU) is integrated into DRL to enhance the deep neural network’s performance. Additionally, to ensure both the maximization of network throughput and the maintenance of fairness among multiple agents, an inspiration mechanism (IM) is proposed to inspire the lazy agent to take more actions to improve its contribution to achieve multi-agent fairness. The simulation results show that the proposed protocol facilitates the convergence of network throughput to optimal levels across various system configurations and environmental conditions.

考虑到水下认知声学传感器网络固有的巨大传播延迟所带来的挑战，本文探讨了多代理深度强化学习在多接入协议设计中的应用。我们处理的是采用不同时隙 MAC 协议的多个传感器节点之间共享信道和时隙的问题。通过所提出的基于多代理深度强化学习（DRL）的多重访问控制（MDRL-MAC）协议，多个智能节点可以独立学习访问可用空闲时隙的策略。考虑到与水下声学信道相关的长传播延迟，我们在 DRL 框架内重新制定了适当的状态、行动和奖励，以应对多重接入挑战并优化网络吞吐量。为了减轻部分可观测性带来的决策偏差，我们在 DRL 中集成了门控递归单元（GRU），以提高深度神经网络的性能。此外，为了确保网络吞吐量的最大化和多个代理之间的公平性，还提出了一种激励机制（IM），以激励懒惰代理采取更多行动来提高其贡献，从而实现多代理公平性。仿真结果表明，在不同的系统配置和环境条件下，所提出的协议有助于网络吞吐量收敛到最佳水平。

{"title":"Multi-agent deep reinforcement learning based multiple access for underwater cognitive acoustic sensor networks","authors":"Yuzhi Zhang, Xiang Han, Ran Bai, Menglei Jia","doi":"10.1016/j.compeleceng.2024.109819","DOIUrl":"10.1016/j.compeleceng.2024.109819","url":null,"abstract":"<div><div>Considering the challenges posed by the significant propagation delays inherent in underwater cognitive acoustic sensor networks, this paper explores the application of multi-agent deep reinforcement learning for the design of multiple access protocols. We deal with the problem of sharing channels and time slots among multiple sensor nodes that adopt different time-slotted MAC protocols. The multiple intelligent nodes can independently learn the strategies for accessing available idle time slots through the proposed multi-agent deep reinforcement learning (DRL) based multiple access control (MDRL-MAC) protocol. Considering the long propagation delay associated with underwater acoustic channels, we reformulate proper state, action, and reward within the DRL framework to address the multiple access challenges and optimize network throughput. To mitigate the decision deviation stemming from partial observability, the gated recurrent unit (GRU) is integrated into DRL to enhance the deep neural network’s performance. Additionally, to ensure both the maximization of network throughput and the maintenance of fairness among multiple agents, an inspiration mechanism (IM) is proposed to inspire the lazy agent to take more actions to improve its contribution to achieve multi-agent fairness. The simulation results show that the proposed protocol facilitates the convergence of network throughput to optimal levels across various system configurations and environmental conditions.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109819"},"PeriodicalIF":4.0,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An effective intrusion detection scheme for Distributed Network Protocol 3 (DNP3) applied in SCADA-enabled IoT applications 适用于 SCADA 物联网应用的分布式网络协议 3 (DNP3) 的有效入侵检测方案

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-11-05 DOI: 10.1016/j.compeleceng.2024.109828

Gagan Dangwal , Saksham Mittal , Mohammad Wazid , Jaskaran Singh , Ashok Kumar Das , Debasis Giri , Mohammed J.F. Alenazi

The widespread adoption of computers and the Internet in recent decades has led to a growing reliance on digital technologies. Supervisory Control and Data Acquisition (SCADA)-enabled Internet of Things (IoT) applications are now used in various sectors such as nuclear power plants, oil and gas extraction, and refineries. However, ensuring the security of computer networks and such autonomous systems is essential to thwart potential threats from hackers and intruders. In this article, an intrusion detection scheme is proposed by deploying different machine learning algorithms (referred to as IDM-DNP3). These algorithms are rigorously trained and tested on an extensive dataset encompassing nine Distributed Network Protocol 3 (DNP3) testbed attacks. Utilizing a range of algorithms, a multi-class classification model was successfully developed for detecting attacks related to SCADA and DNP3. The comparative study conducted shows that IDM-DNP3 can detect potential threats with higher accuracy than other existing schemes.

近几十年来，计算机和互联网的广泛应用使人们越来越依赖数字技术。由监控和数据采集（SCADA）支持的物联网（IoT）应用现已广泛应用于核电站、石油和天然气开采以及炼油厂等各个领域。然而，要抵御黑客和入侵者的潜在威胁，确保计算机网络和此类自主系统的安全至关重要。本文通过部署不同的机器学习算法（简称 IDM-DNP3），提出了一种入侵检测方案。这些算法经过严格训练，并在包含九种分布式网络协议 3 (DNP3) 测试平台攻击的广泛数据集上进行了测试。利用一系列算法，成功开发了一个多类分类模型，用于检测与 SCADA 和 DNP3 相关的攻击。对比研究表明，与其他现有方案相比，IDM-DNP3 能够以更高的准确率检测潜在威胁。

{"title":"An effective intrusion detection scheme for Distributed Network Protocol 3 (DNP3) applied in SCADA-enabled IoT applications","authors":"Gagan Dangwal , Saksham Mittal , Mohammad Wazid , Jaskaran Singh , Ashok Kumar Das , Debasis Giri , Mohammed J.F. Alenazi","doi":"10.1016/j.compeleceng.2024.109828","DOIUrl":"10.1016/j.compeleceng.2024.109828","url":null,"abstract":"<div><div>The widespread adoption of computers and the Internet in recent decades has led to a growing reliance on digital technologies. Supervisory Control and Data Acquisition (SCADA)-enabled Internet of Things (IoT) applications are now used in various sectors such as nuclear power plants, oil and gas extraction, and refineries. However, ensuring the security of computer networks and such autonomous systems is essential to thwart potential threats from hackers and intruders. In this article, an intrusion detection scheme is proposed by deploying different machine learning algorithms (referred to as IDM-DNP3). These algorithms are rigorously trained and tested on an extensive dataset encompassing nine Distributed Network Protocol 3 (DNP3) testbed attacks. Utilizing a range of algorithms, a multi-class classification model was successfully developed for detecting attacks related to SCADA and DNP3. The comparative study conducted shows that IDM-DNP3 can detect potential threats with higher accuracy than other existing schemes.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109828"},"PeriodicalIF":4.0,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142587423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Mitigation of electric field near overhead transmission lines using electromechanical compensation based on genetic algorithm 利用基于遗传算法的机电补偿缓解架空输电线路附近的电场

IF 4 3区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Computers & Electrical Engineering

Pub Date : 2024-11-05 DOI: 10.1016/j.compeleceng.2024.109845

Eslam Mohamed Ahmed , Khaled Hosny Ibrahim

The electrical field is a function of both the voltage and the configuration of the overhead transmission line (OTL); thus, mitigation of the electrical field could be achieved by either electrical compensation or mechanical rearrangement of the line configuration. In the mechanical rearrangement method, the conductor positions are optimized under certain constraints so that the electrical field has the minimum possible value. In the proposed research, OTL mechanical rearrangement is improved using electrical compensation based on a genetic algorithm (GA). The electrical compensation is implemented by inserting a combination of passive series and shunt elements in each phase, creating an electric voltage imbalance. GA is an evolutionary optimization algorithm used to minimize the electric field near residences as a fitness function. The positions of conductors and passive-reactive elements are represented as genes. In addition, this paper includes a case study on a 500-kV high-voltage overhead transmission line. The results show that when passive-reactive compensation is combined with mechanical compensation, the lowest electric field can be obtained. Electrical compensation improves the mechanical rearrangement method by approximately 18.6% (the total reduction with mechanical compensation of only about 34% is increased to more than 52% with electromechanical compensation).

电场是电压和架空输电线路（OTL）配置的函数；因此，可以通过电气补偿或线路配置的机械重排来减轻电场。在机械重新排列法中，导体位置在一定的约束条件下进行优化，从而使电场值尽可能小。在拟议的研究中，基于遗传算法（GA）的电气补偿改进了 OTL 机械重新排列。电气补偿通过在每个相位插入无源串联和并联元件组合来实现，从而产生电压不平衡。遗传算法是一种进化优化算法，用于将住宅附近的电场最小化，作为一种适应度函数。导体和无源反应元件的位置表示为基因。此外，本文还对一条 500 千伏高压架空输电线路进行了案例研究。结果表明，当被动反应补偿与机械补偿相结合时，可以获得最低电场。电气补偿比机械重排法提高了约 18.6%（机械补偿的总降低率仅为 34%，而机电补偿则提高到 52%以上）。

{"title":"Mitigation of electric field near overhead transmission lines using electromechanical compensation based on genetic algorithm","authors":"Eslam Mohamed Ahmed , Khaled Hosny Ibrahim","doi":"10.1016/j.compeleceng.2024.109845","DOIUrl":"10.1016/j.compeleceng.2024.109845","url":null,"abstract":"<div><div>The electrical field is a function of both the voltage and the configuration of the overhead transmission line (OTL); thus, mitigation of the electrical field could be achieved by either electrical compensation or mechanical rearrangement of the line configuration. In the mechanical rearrangement method, the conductor positions are optimized under certain constraints so that the electrical field has the minimum possible value. In the proposed research, OTL mechanical rearrangement is improved using electrical compensation based on a genetic algorithm (GA). The electrical compensation is implemented by inserting a combination of passive series and shunt elements in each phase, creating an electric voltage imbalance. GA is an evolutionary optimization algorithm used to minimize the electric field near residences as a fitness function. The positions of conductors and passive-reactive elements are represented as genes. In addition, this paper includes a case study on a 500-kV high-voltage overhead transmission line. The results show that when passive-reactive compensation is combined with mechanical compensation, the lowest electric field can be obtained. Electrical compensation improves the mechanical rearrangement method by approximately 18.6% (the total reduction with mechanical compensation of only about 34% is increased to more than 52% with electromechanical compensation).</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"120 ","pages":"Article 109845"},"PeriodicalIF":4.0,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142593225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0